This is a note to let you know that I've just added the patch titled
scsi: ibmvfc: Fix command state accounting and stale response detection
to the 5.13-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
scsi-ibmvfc-fix-command-state-accounting-and-stale-response-detection.patch
and it can be found in the queue-5.13 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From a264cf5e81c78e2b9918b8b9ef2ace9dde1850df Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@xxxxxxxxxxxxx>
Date: Fri, 16 Jul 2021 14:52:20 -0600
Subject: scsi: ibmvfc: Fix command state accounting and stale response detection
From: Tyrel Datwyler <tyreld@xxxxxxxxxxxxx>
commit a264cf5e81c78e2b9918b8b9ef2ace9dde1850df upstream.
Prior to commit 1f4a4a19508d ("scsi: ibmvfc: Complete commands outside the
host/queue lock") responses to commands were completed sequentially with
the host lock held such that a command had a basic binary state of active
or free. It was therefore a simple affair of ensuring the assocaiated
ibmvfc_event to a VIOS response was valid by testing that it was not
already free. The lock relexation work to complete commands outside the
lock inadverdently made it a trinary command state such that a command is
either in flight, received and being completed, or completed and now
free. This breaks the stale command detection logic as a command may be
still marked active and been placed on the delayed completion list when a
second stale response for the same command arrives. This can lead to double
completions and list corruption. This issue was exposed by a recent VIOS
regression were a missing memory barrier could occasionally result in the
ibmvfc client receiving a duplicate response for the same command.
Fix the issue by introducing the atomic ibmvfc_event.active to track the
trinary state of a command. The state is explicitly set to 1 when a command
is successfully sent. The CRQ response handlers use
atomic_dec_if_positive() to test for stale responses and correctly
transition to the completion state when a active command is received.
Finally, atomic_dec_and_test() is used to sanity check transistions when
commands are freed as a result of a completion, or moved to the purge list
as a result of error handling or adapter reset.
Link: https://lore.kernel.org/r/20210716205220.1101150-1-tyreld@xxxxxxxxxxxxx
Fixes: 1f4a4a19508d ("scsi: ibmvfc: Complete commands outside the host/queue lock")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Tyrel Datwyler <tyreld@xxxxxxxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/scsi/ibmvscsi/ibmvfc.c | 19 +++++++++++++++++--
drivers/scsi/ibmvscsi/ibmvfc.h | 1 +
2 files changed, 18 insertions(+), 2 deletions(-)
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -804,6 +804,13 @@ static int ibmvfc_init_event_pool(struct
for (i = 0; i < size; ++i) {
struct ibmvfc_event *evt = &pool->events[i];
+ /*
+ * evt->active states
+ * 1 = in flight
+ * 0 = being completed
+ * -1 = free/freed
+ */
+ atomic_set(&evt->active, -1);
atomic_set(&evt->free, 1);
evt->crq.valid = 0x80;
evt->crq.ioba = cpu_to_be64(pool->iu_token + (sizeof(*evt->xfer_iu) * i));
@@ -1014,6 +1021,7 @@ static void ibmvfc_free_event(struct ibm
BUG_ON(!ibmvfc_valid_event(pool, evt));
BUG_ON(atomic_inc_return(&evt->free) != 1);
+ BUG_ON(atomic_dec_and_test(&evt->active));
spin_lock_irqsave(&evt->queue->l_lock, flags);
list_add_tail(&evt->queue_list, &evt->queue->free);
@@ -1069,6 +1077,12 @@ static void ibmvfc_complete_purge(struct
**/
static void ibmvfc_fail_request(struct ibmvfc_event *evt, int error_code)
{
+ /*
+ * Anything we are failing should still be active. Otherwise, it
+ * implies we already got a response for the command and are doing
+ * something bad like double completing it.
+ */
+ BUG_ON(!atomic_dec_and_test(&evt->active));
if (evt->cmnd) {
evt->cmnd->result = (error_code << 16);
evt->done = ibmvfc_scsi_eh_done;
@@ -1720,6 +1734,7 @@ static int ibmvfc_send_event(struct ibmv
evt->done(evt);
} else {
+ atomic_set(&evt->active, 1);
spin_unlock_irqrestore(&evt->queue->l_lock, flags);
ibmvfc_trc_start(evt);
}
@@ -3248,7 +3263,7 @@ static void ibmvfc_handle_crq(struct ibm
return;
}
- if (unlikely(atomic_read(&evt->free))) {
+ if (unlikely(atomic_dec_if_positive(&evt->active))) {
dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
crq->ioba);
return;
@@ -3775,7 +3790,7 @@ static void ibmvfc_handle_scrq(struct ib
return;
}
- if (unlikely(atomic_read(&evt->free))) {
+ if (unlikely(atomic_dec_if_positive(&evt->active))) {
dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
crq->ioba);
return;
--- a/drivers/scsi/ibmvscsi/ibmvfc.h
+++ b/drivers/scsi/ibmvscsi/ibmvfc.h
@@ -744,6 +744,7 @@ struct ibmvfc_event {
struct ibmvfc_target *tgt;
struct scsi_cmnd *cmnd;
atomic_t free;
+ atomic_t active;
union ibmvfc_iu *xfer_iu;
void (*done)(struct ibmvfc_event *evt);
void (*_done)(struct ibmvfc_event *evt);
Patches currently in stable-queue which might be from tyreld@xxxxxxxxxxxxx are
queue-5.13/scsi-ibmvfc-fix-command-state-accounting-and-stale-response-detection.patch
